AI ワークフローに合うスキルを見つけよう。
hypothesis-generation
Formulates evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Used when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.
sentencepiece
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
hypothesis-generation
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.
bio-ctdna-mutation-detection
Detects somatic mutations in circulating tumor DNA, treating low-VAF detection as a signal-versus-noise problem set by error suppression and molecules sampled, not by the choice of caller. Distinguishes de novo CALLING (scanning a panel for unknown variants, bounded by per-locus error and multiple testing) from tumor-informed DETECTION (tracking a pre-speci…
bio-longitudinal-monitoring
Tracks ctDNA across serial liquid-biopsy timepoints for molecular residual disease (MRD) and treatment-response monitoring, treating MRD as a binary integrated detection call across the patient's full variant set (with a defined LoD95 and per-sample specificity) rather than a per-timepoint VAF threshold, and handling undetectable samples as left-censored at…
bio-rna-structure-secondary-structure-prediction
Predicts RNA secondary structure with ViennaRNA, treating the Boltzmann ensemble (partition function, base-pair probabilities, centroid, MEA, stochastic samples) as the object rather than a single MFE fold. Covers consensus folding from alignments (RNAalifold), SHAPE-constrained folding, RNA-RNA interaction (RNAcofold/RNAduplex/RNAup), local and linear-time…
bio-structural-biology-alphafold-predictions
Retrieves and interprets AlphaFold Protein Structure Database (AFDB) models by UniProt accession, reading pLDDT and PAE confidence correctly. Use when treating pLDDT as PER-RESIDUE confidence (not global accuracy) and recognizing a long low-pLDDT stretch as an intrinsically disordered region rather than a modeling error; reading PAE to segment confident dom…
extradition-case-law-search-matei-clej
Searches the domestic courts of 122 jurisdictions — 153 databases, 49 automated — for extradition and arrest-warrant surrender decisions, each in its own language and vocabulary. Answers the question no commercial database does: how are OTHER executing states treating this requesting state, or this ground? Searching by requesting state localises its name pe…
mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies
curating-game-concept-portfolio
Curates a supplied set of game ideas into a small mechanically diverse portfolio by normalizing prose into mechanism signatures, clustering structural duplicates, excluding demonstrated hard failures, comparing available evidence without treating missing data as zero, and selecting for coverage rather than one subjective score. Use for pitch triage, game-ja…
ceo
Strategic operating manual — direction-setting, resource allocation, focus, metrics, and scaling stages for autonomous agents treating themselves as CEO of a one-entity company.
image-to-motion
Turn a single photo, product image, portrait, illustration, or AI artwork into a short image-to-video clip. This AI photo animator and picture-to-video workflow helps you bring a still image to life with directed subject motion, camera movement, pacing, duration, and aspect ratio while treating recognizable faces, product shape, logos, and composition as mu…
accelerator-physicist
Expert-thinking profile for Accelerator Physicist (experimental / beam physics): Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes.
aeronomy-scientist
Expert-thinking profile for Aeronomy Scientist (remote sensing / MLT-thermosphere- ionosphere / ISR + resonance lidar / tides & coupling / empirical models (IRI, NRLMSIS)): Reasons from MLT lidar and ISR profiles through IRI/NRLMSIS benchmarks, treating ion-line spectra, metal-layer winds, and storm-time TEC as distinct observables.
agent-conductor-topology-evolution
Optimize multi-agent collaboration by learning task-specific interaction topologies. Use an LLM orchestrator to generate layered DAG topologies that adapt to inferred problem difficulty, treating agent interactions as a learned graph structure rather than fixed patterns.
agronomist
Expert-thinking profile for Agronomist (field / observational / extension & farm decision support): Reasons from 4R stewardship and G×E×M through MRTN economic N, calibrated soil-test extractants, penetrometer compaction diagnosis, on-farm strip mixed models, partial budgets, and AgroEcoList reporting while treating pseudo- replication, yield-monitor drift,…
aihive-en-content-performance-review
Use for content analytics, content performance, marketing retrospective. Connect published assets to supplied performance exports and propose testable next actions without treating correlation as proof. An AI-HIVE workflow; use supported model-powered steps when needed. Website: https://ai-hive.iclip.cn/chat
amft-meta-learning-alignment
Use meta-learning to automatically balance Supervised Fine-Tuning and Reinforcement Learning signals, treating SFT and RL as complementary rewards in a unified single-stage training framework.
An independently imported catalog with original authors, licenses and source links. Classification is not a security audit.
Sources and import coverage